Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Trade secrets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilage
    -0.06
    :@"
    -0.06
    ment
    -0.06
    userdata
    -0.06
    _MSK
    -0.06
     začala
    -0.06
     관계
    -0.06
     varsa
    -0.06
     brows
    -0.06
    (tweet
    -0.06
    POSITIVE LOGITS
    امت
    0.07
    	Read
    0.07
     consolidate
    0.07
     (...
    0.07
     river
    0.06
    Going
    0.06
     �
    0.06
    getic
    0.06
    0.06
    ,default
    0.06
    Act Density 0.035%

    No Known Activations